Update app.py

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_community.llms import HuggingFaceHub
 from langchain_core.runnables import RunnablePassthrough
 from langchain_core.output_parsers import StrOutputParser
 from langchain.prompts import ChatPromptTemplate
@@ -17,22 +17,22 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 #from transformers import AutoModelForCausalLM
 #from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
 #from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
-from llama_index.llms.huggingface import HuggingFaceInferenceAPI
+#from llama_index.llms.huggingface import HuggingFaceInferenceAPI
 #from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.core import Settings
+#from llama_index.core import Settings
 
 
 #access_token = os.getenv("HUGGINGFACE_API_KEY")
 
 # Configure the Llama index settings
-llm = HuggingFaceInferenceAPI(
-    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    context_window=3900,
-    token=os.getenv("HUGGINGFACE_API_KEY"),
+#llm = HuggingFaceInferenceAPI(
+#    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
+ #   tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
+  #  context_window=3900,
+  #  token=os.getenv("HUGGINGFACE_API_KEY"),
     # max_new_tokens=1000,
-    generate_kwargs={"temperature": 0.1},
-)
+  #  generate_kwargs={"temperature": 0.1},
+#)
 
 
 #st.set_page_config(page_title="Document Genie", layout="wide")
@@ -112,7 +112,13 @@ def get_conversational_chain(retriever):
     #model_id="gpt2",
     #task="text-generation",
     #pipeline_kwargs={"max_new_tokens": 10})
+    #from langchain_community.llms import HuggingFaceHub
 
+    llm = HuggingFaceHub(
+    repo_id="HuggingFaceH4/zephyr-7b-beta",
+    huggingfacehub_api_token="<HF_TOKEN_HERE>",
+    task="text-generation",
+    )
     pt = ChatPromptTemplate.get_template(prompt_template)
     # Retrieve and generate using the relevant snippets of the blog.
     #retriever = db.as_retriever()